Challenges of Context and Time in Reinforcement Learning: Introducing Space Fortress as a Benchmark

Agarwal, Akshat; Hope, Ryan; Sycara, Katia

doi:10.48550/arxiv.1809.02206

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we propose a human-model-free adaptive agent architecture based on a pre-trained static agent library. The adaptive agent aims to perform well in a nontrivial realtime strategic game, Team Space Fortress (TSF) (Agarwal, Hope, and Sycara 2018). TSF is a two-player cooperative computer game where the players control spaceships to destroy the fortress.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Agent Architecture for Real-time Human-Agent Teaming

Ni,

Li,

Agrawal

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Teamwork is a set of interrelated reasoning, actions and behaviors of team members that facilitate common objectives. Teamwork theory and experiments have resulted in a set of states and processes for team effectiveness in both humanhuman and agent-agent teams. However, human-agent teaming is less well studied because it is so new and involves asymmetry in policy and intent not present in human teams. To optimize team performance in human-agent teaming, it is critical that agents infer human intent and adapt their polices for smooth coordination. Most literature in human-agent teaming builds agents referencing a learned human model. Though these agents are guaranteed to perform well with the learned model, they lay heavy assumptions on human policy such as optimality and consistency, which is unlikely in many real-world scenarios. In this paper, we propose a novel adaptive agent architecture in human-model-free setting on a twoplayer cooperative game, namely Team Space Fortress (TSF). Previous human-human team research have shown complementary policies in TSF game and diversity in human players' skill, which encourages us to relax the assumptions on human policy. Therefore, we discard learning human models from human data, and instead use an adaptation strategy on a pre-trained library of exemplar policies composed of RL algorithms or rule-based methods with minimal assumptions of human behavior. The adaptation strategy relies on a novel similarity metric to infer human policy and then selects the most complementary policy in our library to maximize the team performance. The adaptive agent architecture can be deployed in real-time and generalize to any off-the-shelf static agents. We conducted human-agent experiments to evaluate the proposed adaptive agent framework, and demonstrated the suboptimality, diversity, and adaptability of human policies in human-agent teams.* indicates equal contribution. In AAAI 2021 Workshop on Plan, Activity, and Intent Recognition.

show abstract

Section: Introductionmentioning

confidence: 99%